Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2608.20362v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a standard recipe for training large language models on mathematical reasoning, where an ans...
The study presents a reinforcement learning approach, Advantage Aggregation (AdvA), to control the X‑point target (XPT) divertor in the EXL‑50U tokamak experiment. By preserving objective‑wise temporal credit and applying a residual correction, AdvA‑PPO outperforms standard Reward‑PPO and a feedforward‑plus‑PID baseline, achieving a 0.81 worst‑channel score and reducing X‑point flux RMSE by roughly 20× over a 500 ms rollout. The method remains robust under measurement uncertainties and across varied initial equilibria, offering a simulation‑based foundation for future real‑time XPT validation on EXL‑50U.
arXiv:2608.20814v1 Announce Type: new Abstract: Though Multimodal Large Language Models (MLLMs) have shown impressive potential in video understanding, long video understanding (LVU) remains challeng...
arXiv:2608.20909v1 Announce Type: new Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...
The paper introduces Conformalized Agentic Search (CAS), a framework that applies Conformal Prediction to improve the reliability of search agents during reinforcement learning fine-tuning. CAS uses an Adaptive Prediction Set (APS) to dynamically truncate retrieved documents based on statistical coverage, and Adaptive Conformal Inference (ACI) to construct confidence-aware prediction sets that penalize low‑confidence trajectories in the Group Relative Policy Optimization objective. Experiments on single‑hop and multi‑hop QA datasets show that CAS enhances reasoning accuracy and reduces redundant tool invocations, offering a more reliable and efficient agent paradigm.
arXiv:2601.04786v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction,...
arXiv:2608.21175v1 Announce Type: cross Abstract: Safe and efficient shape-aware navigation in heterogeneous crowds and robot fleets remains challenging. Traditional approaches often assume homogeneo...
arXiv:2106.06060v4 Announce Type: replace-cross Abstract: Traditional competitive markets do not account for negative externalities; indirect costs that some participants impose on others, such as th...
arXiv:2608.20858v1 Announce Type: cross Abstract: Transportation networks, in particular multi-class transportation networks (i.e., networks with mixed vehicle types), are complex systems that are ch...
BIPPO (Budget-aware Independent Proximal Policy Optimization) is a multi‑agent reinforcement learning framework designed for energy‑efficient client selection in federated learning (FL) over IoT systems. It addresses infrastructure constraints such as limited resources and device churn, which traditional FL and RL approaches overlook. Evaluated on two image‑classification tasks with non‑IID data, BIPPO improves mean accuracy over non‑RL methods, standard PPO, and IPPO while consuming only a negligible portion of the budget, even as client numbers grow.
The paper introduces reinforcement learning for Continuous-Time Jump Markov Decision Processes (CTJMDPs) with general discrete state spaces and continuous/discrete actions. It develops entropy‑regularized continuous‑time control and establishes theoretical foundations for q‑learning in this setting, providing model‑free algorithms that outperform naive discretization. Numerical tests on network dynamic pricing demonstrate the method’s ability to learn near‑optimal policies and scale to large networks.
The paper explores how dense, turn-level reward structures can improve reinforcement learning for large language model agents in multi-turn tasks. It introduces three reward granularity types—terminal, delayed, and per-turn—and adapts Group Relative Policy Optimization and Proximal Policy Optimization to each. Experiments on search and game agents show that per-turn rewards consistently yield better training dynamics, faster convergence, and higher answer correctness compared to sparse terminal or delayed rewards.
The paper proposes a two-stage personalized thermal comfort system that combines multimodal physiological and environmental sensing with reinforcement learning for decision-making. It aims to move beyond static HVAC setpoints and generic comfort models by tailoring thermal interventions to individual physiological variability. The approach seeks to improve occupant wellbeing and enable more responsive building-control strategies.
Agent skills, structured artifacts distilled from interaction trajectories and dynamically reused from skill banks, have become a central mechanism for enabling large language model (LLM)-based self-e...
World models enable agents to reason about future outcomes and learn policies from their knowledge of state transition, but existing approaches primarily focus on reconstructing future observations or...
arXiv:2605. 06094v5 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories.
arXiv:2605. 10546v2 Announce Type: replace Abstract: Pixel-based deep reinforcement learning agents are typically trained on heavily downsampled visual observations, a convention inherited from early benchmarks rather than grounded in principled design.
arXiv:2608. 19857v1 Announce Type: new Abstract: For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data.
arXiv:2608. 19803v1 Announce Type: cross Abstract: Credit assignment is challenging in long-horizon agentic reinforcement learning, where supervision often comes only from final rewards.
arXiv:2608. 19880v1 Announce Type: new Abstract: LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves.